© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8867
    Prev
    Next
    INDEX
    Explanations

    Code/UI/Technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĹłæķĮ
    -0.26
    #[
    -0.26
     пÑĢÑı
    -0.26
    çļĦæľĢ大
    -0.25
    éĶ¡
    -0.24
    çĶŁæ´»
    -0.24
    æİ©çĽĸ
    -0.24
    æ§Ľ
    -0.24
    udos
    -0.24
     Flood
    -0.23
    POSITIVE LOGITS
     begun
    0.26
     Maui
    0.26
    SETS
    0.25
    -java
    0.25
    liqu
    0.25
    鹿
    0.25
    .raises
    0.24
    quirer
    0.24
    ettes
    0.24
    ancode
    0.24
    Activations Density 0.791%

    No Known Activations